Recurrent neural network-based prediction of compressive and flexural strength of steel slag mixed concrete
- PDF / 1,609,285 Bytes
- 13 Pages / 595.276 x 790.866 pts Page_size
- 105 Downloads / 256 Views
(0123456789().,-volV)(0123456789().,-volV)
ORIGINAL ARTICLE
Recurrent neural network-based prediction of compressive and flexural strength of steel slag mixed concrete Tanvi Gupta1
•
S. N. Sachdeva1
Received: 7 January 2020 / Accepted: 26 October 2020 Ó Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract In this paper, an effort has been made to develop a recurrent type of neural network known as diagonal recurrent neural network (DRNN) to predict the compressive and flexural strengths of AOD steel slag-mixed concrete for pavements. The data used for modeling were attained from the laboratory experiments. The compressive and flexural strengths were experimentally analyzed for specimens containing 0%, 10%, 15%, 20%, and 25% of AOD steel slag as a partial replacement of cement at curing ages of 3, 7, 28, 90, 180, and 365 days. The developed model was trained using the backpropagation (BP) algorithm. The performance of the proposed model during the training and validation has been compared with the well-known prediction models such as multi-layer perceptron (MLP) and the radial basis function network (RBFN). The DRNN-based prediction model has given much better prediction results when compared to the other two models since the former provided comparatively smaller values of performance indicators such as average mean square error (AMSE) and mean average error (MAE). The reason for DRNN performing better than the other two models is that it contains feedback connections/weights which induce memory property in its structure. This helps DRNN to better model the complex mappings. Such feedback loops are not available in MLP and RBFN. The study conducted in this research concludes that the DRNN-based prediction model should be preferred over the MLP and RBFN models for predicting the compressive and flexural strengths of AOD steel slag added to concrete for pavements. Keywords Diagonal recurrent neural network AOD steel slag Concrete Compressive and flexural strengths
1 Introduction Concrete is the life line of all the construction and infrastructure industry [1]. Due to the strength characteristics, durability properties, and affordability of concrete, it has become the maximum used 4 resource after air and water. But concrete is also responsible for carbon dioxide emission which leads to environment pollution [2]. Cement is one of the most important constituents of concrete, and the strength and other properties of concrete highly depend upon both quality and quantity of cement. For the production of stainless steel, recycled iron scrap is processed & Tanvi Gupta [email protected]; [email protected] S. N. Sachdeva [email protected] 1
Department of Civil Engineering, National Institute of Technology, Kurukshetra 136119, India
in electric arc furnace and further refined in the argon oxygen decarburization (AOD) containers. Therefore, the two slags generated at the time of manufacturing of stainless steel are: AOD steel slag and EAF (Electric Arc Furnace) steel slag [3]. U
Data Loading...
